{"id":"W6966711030","doi":"10.48448/gjda-fy41","title":"PiCor: Multi-Task Deep Reinforcement Learning with Policy Correction","year":2023,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Task (project management); Constraint (computer-aided design); Control (management); Sample (material); Compounding; Interference (communication)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001325971,0.00113972,0.0009376495,0.0003107761,0.0003412353,0.0007509256,0.002343584,0.001181404,0.003726625],"category_scores_gemma":[0.002675355,0.0005112521,0.0004771707,0.0002958646,0.0008071085,0.001125987,0.001695404,0.002038901,0.001108569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008134395,"about_ca_system_score_gemma":0.002121596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005317804,"about_ca_topic_score_gemma":0.007327321,"domain_scores_codex":[0.9994272,0.0001376639,0.00002909763,0.0001586348,0.0001576914,0.00008966994],"domain_scores_gemma":[0.9993516,0.0001887441,0.0001053355,0.0001617507,0.000108016,0.0000846176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002820634,0.000311082,0.00101987,0.0001677191,0.0001082978,0.0001379862,0.00005068301,0.7035345,0.007597671,0.01284786,0.009180606,0.2647617],"study_design_scores_gemma":[0.00001627264,0.00003259533,0.00005210164,0.000004097989,0.000003952987,0.00001091604,0.00000159701,0.9965405,0.001059383,0.001568511,0.0007046922,0.000005308643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01066167,0.0003190877,0.9800586,0.000262792,0.0000929681,0.0001005638,0.00008712016,0.004926152,0.003490906],"genre_scores_gemma":[0.6133652,0.0002534798,0.3734354,0.0006271398,0.00008336578,0.0003220217,0.0003842008,0.0005381776,0.01099108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005317804,"threshold_uncertainty_score":0.01246685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02307826103668365,"score_gpt":0.3051186165160267,"score_spread":0.2820403554793431,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}